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

    Neuronpedia

    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     towards
    -0.07
    변
    -0.06
     рав
    -0.06
    ippet
    -0.06
     अव
    -0.06
    ΩΝ
    -0.06
    Freedom
    -0.06
    uye
    -0.06
    \Core
    -0.06
    assadors
    -0.06
    POSITIVE LOGITS
    ethoven
    0.06
     İstanbul
    0.06
    arc
    0.06
    (Create
    0.06
    사이트
    0.06
    /pp
    0.06
     heels
    0.06
    (arc
    0.06
    .oper
    0.06
    krvldkf
    0.06
    Act Density 0.000%

    No Known Activations