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

    Neuronpedia

    INDEX
    Explanations

    abstract math

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ramer
    -0.07
     peripheral
    -0.07
     apartment
    -0.07
     Preferences
    -0.07
    唇
    -0.07
     furniture
    -0.07
    acija
    -0.06
    elize
    -0.06
     invites
    -0.06
     Vermont
    -0.06
    POSITIVE LOGITS
    .blob
    0.06
    904
    0.06
    olv
    0.06
    _SELECTED
    0.06
    失
    0.06
    जन
    0.06
    итися
    0.06
     epit
    0.06
    ',{'
    0.06
     εγκα
    0.06
    Act Density 0.036%

    No Known Activations