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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bounty
    -0.07
     fame
    -0.07
    aac
    -0.07
     �
    -0.06
    hei
    -0.06
    page
    -0.06
    _house
    -0.06
    άνα
    -0.06
     mục
    -0.06
     bom
    -0.06
    POSITIVE LOGITS
     cheap
    0.07
    VarInsn
    0.06
     Finn
    0.06
     вида
    0.06
     Elsa
    0.06
     Costa
    0.06
    fig
    0.06
    Scalars
    0.06
    _branch
    0.06
    』
    0.06
    Act Density 0.000%

    No Known Activations