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

    Neuronpedia

    INDEX
    Explanations

    Unchanging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (quantity
    -0.07
    slot
    -0.07
     "-",
    -0.07
     einzel
    -0.07
     pessoa
    -0.06
     thrift
    -0.06
     rhet
    -0.06
    ол
    -0.06
     felony
    -0.06
    /cgi
    -0.06
    POSITIVE LOGITS
     unchanged
    0.11
     unaffected
    0.08
     untouched
    0.08
    Regardless
    0.07
     ราคา
    0.07
     Korean
    0.06
     Regardless
    0.06
    :g
    0.06
     Freed
    0.06
     pristine
    0.06
    Act Density 0.007%

    No Known Activations