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

    Neuronpedia

    INDEX
    Explanations

    ref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    者
    -0.07
     owl
    -0.07
    Supplier
    -0.07
     Ocean
    -0.07
     SUN
    -0.07
     Roman
    -0.07
     daddy
    -0.06
     Requirement
    -0.06
     darker
    -0.06
     Wind
    -0.06
    POSITIVE LOGITS
    fer
    0.08
    .predict
    0.07
    received
    0.06
     putting
    0.06
    ková
    0.06
     infer
    0.06
     Γου
    0.06
    _article
    0.06
    virt
    0.06
    ernels
    0.06
    Act Density 0.002%

    No Known Activations