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

    Neuronpedia

    INDEX
    Explanations

    asking questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лением
    -0.07
    Ids
    -0.07
    -week
    -0.06
     θεω
    -0.06
     cleanup
    -0.06
     Vault
    -0.06
    pec
    -0.06
     lineup
    -0.06
    Vs
    -0.06
    photos
    -0.06
    POSITIVE LOGITS
     Will
    0.07
     will
    0.07
     would
    0.07
     ขนาด
    0.07
    ),"
    0.07
     Clin
    0.07
    would
    0.07
     shall
    0.07
     분류
    0.06
    алася
    0.06
    Act Density 0.060%

    No Known Activations