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

    Neuronpedia

    INDEX
    Explanations

    less

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cop
    -0.07
    isdiction
    -0.07
     prof
    -0.06
     charcoal
    -0.06
    Having
    -0.06
     Ling
    -0.06
     Boyd
    -0.06
     developers
    -0.06
     Lots
    -0.06
     jurisdiction
    -0.06
    POSITIVE LOGITS
    .volley
    0.07
    ']");↵
    0.07
    塑
    0.07
    校
    0.07
    .EXIT
    0.07
    _TypeDef
    0.07
    forgettable
    0.06
    кус
    0.06
    educated
    0.06
    ในร
    0.06
    Act Density 0.006%

    No Known Activations