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

    Neuronpedia

    INDEX
    Explanations

    Douglas Adams, Hacking, mimicking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ）』
    0.55
    )},\
    0.54
    )),
    0.52
     abduction
    0.50
     investigators
    0.50
     uncovering
    0.50
     निकाले
    0.50
     ultrast
    0.49
    বঙ্গ
    0.49
     Geißler
    0.48
    POSITIVE LOGITS
    U
    0.68
    I
    0.64
    D
    0.62
    ו
    0.57
    isiones
    0.54
    ID
    0.53
    User
    0.52
    A
    0.52
    <0x9A>
    0.51
    ENCIA
    0.50
    Act Density 0.000%

    No Known Activations