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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     signatures
    -0.06
    .begin
    -0.06
     Scho
    -0.06
     bakımından
    -0.06
     hidden
    -0.06
    Smooth
    -0.06
     Nacional
    -0.06
    -three
    -0.06
    #!/
    -0.06
     removeFrom
    -0.06
    POSITIVE LOGITS
    plaint
    0.07
    ран
    0.07
    usp
    0.06
    forg
    0.06
    _hits
    0.06
     pokus
    0.06
    луги
    0.06
    ryan
    0.06
    invite
    0.06
     fall
    0.06
    Act Density 0.067%

    No Known Activations