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

    Neuronpedia

    INDEX
    Explanations

    philipp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     tard
    -0.07
     během
    -0.07
    478
    -0.06
    673
    -0.06
     noci
    -0.06
     soc
    -0.06
    雑
    -0.06
     Rosen
    -0.06
    475
    -0.06
    POSITIVE LOGITS
    logy
    0.08
    -property
    0.07
     bill
    0.06
    .Collectors
    0.06
    Aligned
    0.06
    PU
    0.06
     Phil
    0.06
     thầu
    0.06
    .contact
    0.06
     Pipeline
    0.06
    Act Density 0.019%

    No Known Activations