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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BI
    -0.07
    conv
    -0.07
     disclosing
    -0.07
    ाब
    -0.07
     nef
    -0.06
    .Ignore
    -0.06
     skips
    -0.06
     emph
    -0.06
    jan
    -0.06
     Lodge
    -0.06
    POSITIVE LOGITS
     subTitle
    0.07
     RES
    0.06
     Amy
    0.06
    Who
    0.06
    keh
    0.06
    _comparison
    0.06
    })↵↵↵
    0.06
     ACA
    0.06
     RETURN
    0.06
     vyj
    0.06
    Act Density 0.000%

    No Known Activations