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

    Neuronpedia

    INDEX
    Explanations

    polystyrene

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beast
    -0.07
    .tag
    -0.06
    Receiver
    -0.06
     itself
    -0.06
    another
    -0.06
     ts
    -0.06
    nt
    -0.06
     themselves
    -0.06
    .vn
    -0.06
     deadly
    -0.06
    POSITIVE LOGITS
    \admin
    0.07
    рив
    0.07
    (layers
    0.07
     موقعیت
    0.07
    conciliation
    0.06
    RULE
    0.06
    .visitMethodInsn
    0.06
     mascul
    0.06
     unreasonable
    0.06
     libero
    0.06
    Act Density 0.001%

    No Known Activations