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

    Neuronpedia

    INDEX
    Explanations

    applications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /-
    -0.08
    丽
    -0.06
     Printed
    -0.06
    _prep
    -0.06
     rack
    -0.06
     convo
    -0.06
     pit
    -0.06
     loose
    -0.06
    兵
    -0.06
    >}
    -0.06
    POSITIVE LOGITS
    .curr
    0.07
    recover
    0.07
    _ALIGN
    0.06
    łą
    0.06
     skvěl
    0.06
     Rendering
    0.06
    _holder
    0.06
    Ruby
    0.06
    živ
    0.06
     reson
    0.06
    Act Density 0.036%

    No Known Activations