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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     horrors
    -0.07
    ㅋ
    -0.06
     Word
    -0.06
     cover
    -0.06
     declaration
    -0.06
     lien
    -0.06
    -id
    -0.06
     noon
    -0.06
     tradi
    -0.06
     nin
    -0.06
    POSITIVE LOGITS
    riet
    0.07
    ुगत
    0.07
    .resolve
    0.06
     Guidelines
    0.06
     []);↵↵
    0.06
    .TestCheck
    0.06
    -producing
    0.06
    yer
    0.06
    .Equal
    0.06
    чет
    0.06
    Act Density 0.000%

    No Known Activations