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

    Neuronpedia

    INDEX
    Explanations

    square root domains

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     confused
    -0.09
     Tudor
    -0.08
     недели
    -0.08
     Glasgow
    -0.08
     annoyed
    -0.08
    联系方式
    -0.08
     negotiating
    -0.08
    श्रेष्ठ
    -0.08
     Negoti
    -0.08
     Jerseys
    -0.08
    POSITIVE LOGITS
     >=
    0.10
     ≥
    0.10
    .ZERO
    0.09
     positivity
    0.09
     పరిస్థిత
    0.08
    మే
    0.08
    >=
    0.08
    ≥
    0.08
     ముంద
    0.08
     emoz
    0.08
    Act Density 0.031%

    No Known Activations