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

    Neuronpedia

    INDEX
    Explanations

    var

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CASCADE
    -0.07
    öy
    -0.06
    vailable
    -0.06
    �
    -0.06
    ήν
    -0.06
    -follow
    -0.06
    uitar
    -0.06
    IÓN
    -0.06
    ampionship
    -0.06
     publicity
    -0.06
    POSITIVE LOGITS
     tags
    0.07
     most
    0.07
    >R
    0.06
     deriving
    0.06
     technology
    0.06
     Frank
    0.06
     dosp
    0.06
     Meet
    0.06
     preventing
    0.06
     Host
    0.06
    Act Density 0.018%

    No Known Activations