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

    Neuronpedia

    INDEX
    Explanations

    v

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tek
    -0.07
    ))*(
    -0.07
     Positive
    -0.07
     reader
    -0.06
    =-
    -0.06
     Fischer
    -0.06
    ір
    -0.06
     grabbed
    -0.06
     lékař
    -0.06
     Stef
    -0.06
    POSITIVE LOGITS
    μα
    0.06
    inputEmail
    0.06
    sort
    0.06
    (lock
    0.06
    _TX
    0.06
    avour
    0.06
    LEAN
    0.06
    ogy
    0.06
     �
    0.06
     Bias
    0.06
    Act Density 0.001%

    No Known Activations