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

    Neuronpedia

    INDEX
    Explanations

    Size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HOLDER
    -0.08
    .Are
    -0.07
     congressional
    -0.07
     jeunes
    -0.07
     emo
    -0.07
    _${
    -0.07
     Israelis
    -0.07
    有的
    -0.06
    ocrat
    -0.06
     어디
    -0.06
    POSITIVE LOGITS
     Púb
    0.07
     Borg
    0.07
    念佛
    0.07
    ила
    0.07
    _disconnect
    0.07
     starvation
    0.06
    Projection
    0.06
    itative
    0.06
     défini
    0.06
    identifier
    0.06
    Act Density 0.029%

    No Known Activations