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

    Neuronpedia

    INDEX
    Explanations

    Quantities and comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    buz
    -0.08
     serviços
    -0.07
     davran
    -0.07
     urgency
    -0.07
    “
    -0.07
    .documentation
    -0.07
    -step
    -0.07
    "
    -0.07
     pkg
    -0.06
    .launch
    -0.06
    POSITIVE LOGITS
    링
    0.06
     неболь
    0.06
    (=
    0.06
    :key
    0.06
     miners
    0.06
    /en
    0.05
     experimenting
    0.05
     Considering
    0.05
    �다
    0.05
    벌
    0.05
    Act Density 0.044%

    No Known Activations