Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to machinery and mechanical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numbers, especially decimals

    np_acts-logits-general · gemini-2.0-flash

    projectile whose flight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.47
     nakalista
    -0.46
     FIFA
    -0.45
     gio
    -0.45
     Kun
    -0.44
     Comédie
    -0.43
    falgar
    -0.43
    naive
    -0.42
    حياتها
    -0.42
     demo
    -0.42
    POSITIVE LOGITS
     bullet
    0.56
     bullets
    0.52
    WireFormatLite
    0.48
     ammo
    0.48
    bullet
    0.47
     reload
    0.46
     ammunition
    0.45
     reloading
    0.45
     jacke
    0.45
    Bullet
    0.45
    Act Density 0.168%

    No Known Activations