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

    Neuronpedia

    INDEX
    Explanations

    Verb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    diği
    -0.08
    figcaption
    -0.07
     Phi
    -0.06
     snapshot
    -0.06
     miserable
    -0.06
     alloy
    -0.06
     Granite
    -0.06
    ीस
    -0.06
    -Bold
    -0.06
     parl
    -0.06
    POSITIVE LOGITS
    (firstName
    0.08
    (food
    0.07
    _EXIT
    0.07
    .INTERNAL
    0.07
    .String
    0.07
    ент
    0.06
    bellion
    0.06
    (inv
    0.06
    ORT
    0.06
     trời
    0.06
    Act Density 0.095%

    No Known Activations