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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     balans
    -0.10
     samun
    -0.09
     రోజ
    -0.08
    ालत
    -0.08
    余额
    -0.08
     dagdag
    -0.08
    atah
    -0.08
     betaalt
    -0.08
     rara
    -0.07
    ంట
    -0.07
    POSITIVE LOGITS
    .Setup
    0.09
    Implement
    0.09
     convenient
    0.09
     représentant
    0.08
    maybe
    0.08
     devise
    0.08
     approach
    0.08
    manager
    0.08
     maybe
    0.08
     implement
    0.08
    Act Density 0.016%

    No Known Activations