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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     writable
    -0.06
     rever
    -0.06
     getCode
    -0.06
    (factor
    -0.06
    ffset
    -0.06
     cooking
    -0.06
     supremacist
    -0.06
    Scient
    -0.06
     "',
    -0.06
    (".")
    -0.06
    POSITIVE LOGITS
    či
    0.06
    olik
    0.06
    له
    0.06
     mole
    0.06
     LM
    0.06
    제
    0.06
     leaf
    0.06
     adequately
    0.06
    .Errorf
    0.06
     Stokes
    0.06
    Act Density 0.074%

    No Known Activations