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
    .orig
    -0.07
    řit
    -0.07
    ('/')[
    -0.07
     انر
    -0.06
    емо
    -0.06
    .Out
    -0.06
     нор
    -0.06
    /editor
    -0.06
     bạc
    -0.06
    .Internal
    -0.06
    POSITIVE LOGITS
     clipboard
    0.07
     Toyota
    0.06
     counselor
    0.06
     invisible
    0.06
     created
    0.06
     create
    0.06
    属
    0.06
    ัตถ
    0.05
    .Immutable
    0.05
     manufactured
    0.05
    Act Density 0.000%

    No Known Activations