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

    Neuronpedia

    INDEX
    Explanations

    again

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assassination
    -0.06
    004
    -0.06
    ahrenheit
    -0.06
    149
    -0.06
     intimid
    -0.06
     thinks
    -0.06
    =x
    -0.06
    .getDay
    -0.06
     연구
    -0.06
    wendung
    -0.06
    POSITIVE LOGITS
    encion
    0.08
    odel
    0.06
    food
    0.06
     करत
    0.06
    orum
    0.06
     Essential
    0.06
    (group
    0.06
     nouvelle
    0.06
    (sheet
    0.06
    носят
    0.06
    Act Density 0.022%

    No Known Activations