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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions related to changing or improving situations

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

    mix or shakes up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.49
     nakalista
    -0.48
     disambiguazione
    -0.48
    Datuak
    -0.46
     Infórmanos
    -0.45
    Erreferentziak
    -0.39
    adaptiveStyles
    -0.36
    /**
    -0.36
     zeitung
    -0.36
    BrowserModule
    -0.36
    POSITIVE LOGITS
    mix
    0.65
    Mix
    0.62
     mix
    0.61
     mixes
    0.61
     Mix
    0.58
    MIX
    0.58
     MIX
    0.58
     mixtures
    0.51
     Mischung
    0.50
    Shuffle
    0.50
    Act Density 0.005%

    No Known Activations