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

    Neuronpedia

    INDEX
    Explanations

    sed commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    compound
    -0.06
    、その
    -0.06
     ledna
    -0.06
    _repeat
    -0.06
     decent
    -0.06
    arend
    -0.06
     sob
    -0.06
    ασ
    -0.06
     один
    -0.06
    ussian
    -0.06
    POSITIVE LOGITS
     budget
    0.07
    hero
    0.07
    Budget
    0.07
     penis
    0.07
    upy
    0.07
    telefono
    0.07
    aul
    0.07
    лях
    0.06
    urrets
    0.06
     Tau
    0.06
    Act Density 0.002%

    No Known Activations