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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     faculty
    -0.06
     Thorn
    -0.06
    _rb
    -0.06
    ajo
    -0.06
     FY
    -0.06
     persisted
    -0.06
     hood
    -0.06
     cultivate
    -0.06
    586
    -0.06
     advise
    -0.06
    POSITIVE LOGITS
     defaultstate
    0.07
     Cox
    0.07
    Configure
    0.07
    ubu
    0.07
    .eye
    0.07
     ECC
    0.06
    ]=$
    0.06
    ụp
    0.06
     savoir
    0.06
     HMS
    0.06
    Act Density 0.080%

    No Known Activations