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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _perm
    -0.07
     critiques
    -0.06
    _TEAM
    -0.06
     polynomial
    -0.06
    �
    -0.06
     prominence
    -0.06
     accumulate
    -0.06
     weakest
    -0.06
     deline
    -0.06
     objeto
    -0.06
    POSITIVE LOGITS
    .`,↵
    0.08
     knife
    0.07
    込
    0.06
     sanity
    0.06
    elleicht
    0.06
    .gridx
    0.06
     می
    0.06
    fprintf
    0.06
     चरण
    0.06
    Tôi
    0.06
    Act Density 0.026%

    No Known Activations