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

    Neuronpedia

    INDEX
    Explanations

    Staring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hari
    -0.08
    Minimum
    -0.08
    ewise
    -0.07
     infusion
    -0.07
    -inf
    -0.07
    minimum
    -0.07
    overwrite
    -0.07
    semi
    -0.07
     overwrite
    -0.07
     indie
    -0.07
    POSITIVE LOGITS
     captivated
    0.09
     dizziness
    0.09
     mental
    0.08
     முழ
    0.08
     മുഴ
    0.08
     الذات
    0.08
    ันท
    0.08
     mentally
    0.08
     diens
    0.08
     Mental
    0.08
    Act Density 0.002%

    No Known Activations