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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SNP
    -0.07
     сор
    -0.07
     쪽지
    -0.06
    沿
    -0.06
     Buddhism
    -0.06
     Ả
    -0.06
     nationality
    -0.06
    (provider
    -0.06
    OrFail
    -0.06
    μα
    -0.06
    POSITIVE LOGITS
    umbledore
    0.07
    ccd
    0.07
    /nav
    0.07
    conditional
    0.07
     allev
    0.07
     poate
    0.07
    CC
    0.07
     boots
    0.06
     José
    0.06
    Biz
    0.06
    Act Density 0.000%

    No Known Activations