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

    Neuronpedia

    INDEX
    Explanations

    register fingerprint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Countdown
    0.45
     topologies
    0.44
    Ст
    0.44
    <0xD0>
    0.43
    Blueprint
    0.42
    Aquí
    0.41
    WARF
    0.40
    Leu
    0.40
    ugía
    0.39
    तं
    0.39
    POSITIVE LOGITS
     downside
    0.50
     slightly
    0.48
     leider
    0.48
     co
    0.47
     go
    0.45
     aided
    0.44
     ki
    0.42
     h
    0.41
     hu
    0.41
     Go
    0.41
    Act Density 0.001%

    No Known Activations