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

    Neuronpedia

    INDEX
    Explanations

    code documentation comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ))*
    0.78
    *)
    0.76
    Var
    0.70
    )**
    0.68
    यर
    0.68
     तिचा
    0.67
    ophysics
    0.67
    )*
    0.66
    daki
    0.64
     *)
    0.64
    POSITIVE LOGITS
     wines
    0.81
     Paco
    0.76
     गिवन
    0.75
     सकारात्मक
    0.74
    誅
    0.73
     Skills
    0.71
     गिव
    0.71
     Detox
    0.71
    ₡
    0.71
     მხოლოდ
    0.70
    Act Density 0.001%

    No Known Activations