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

    Neuronpedia

    INDEX
    Explanations

    statistical analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    him
    -0.08
    ktop
    -0.08
    igious
    -0.08
     　
    -0.07
     mình
    -0.07
    buttons
    -0.07
     ибо
    -0.07
    gebra
    -0.07
    金
    -0.07
    가지
    -0.07
    POSITIVE LOGITS
     decreasing
    0.09
     increasing
    0.09
     succesvolle
    0.08
     decrease
    0.08
     PLA
    0.08
     increase
    0.08
     succesvol
    0.08
     diminishing
    0.08
     negatively
    0.08
    Increasing
    0.08
    Act Density 0.008%

    No Known Activations