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

    Neuronpedia

    INDEX
    Explanations

    positive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rebellion
    -0.07
    HELL
    -0.07
     halted
    -0.06
     Desk
    -0.06
     laptop
    -0.06
     hemat
    -0.06
     cell
    -0.06
     Shore
    -0.06
     Amph
    -0.06
    ़ो
    -0.06
    POSITIVE LOGITS
     means
    0.06
    undred
    0.06
    ayas
    0.06
    .Nome
    0.06
    liable
    0.06
    PLEASE
    0.06
    dire
    0.06
    .Decode
    0.06
     está
    0.06
     konk
    0.06
    Act Density 0.004%

    No Known Activations