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

    Neuronpedia

    INDEX
    Explanations

    existing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     처음
    -0.08
     Alp
    -0.08
    แรก
    -0.07
    Extras
    -0.07
     kisses
    -0.07
     Farrell
    -0.07
    гаар
    -0.07
     Extras
    -0.07
     Ane
    -0.07
     Kim
    -0.07
    POSITIVE LOGITS
     existente
    0.10
    -existing
    0.10
    existing
    0.10
    -fashioned
    0.09
     besta
    0.09
     byl
    0.09
    ところ
    0.08
     থেকেই
    0.08
    (existing
    0.08
     wisdom
    0.08
    Act Density 0.015%

    No Known Activations