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

    Neuronpedia

    INDEX
    Explanations

    block start after parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ={"
    0.86
     keeps
    0.83
    keeps
    0.81
     looks
    0.81
    looks
    0.80
    feels
    0.80
    missione
    0.79
     eases
    0.77
     engages
    0.76
    водит
    0.75
    POSITIVE LOGITS
     continue
    1.04
    continue
    0.86
     return
    0.77
     ((
    0.77
     ++
    0.75
     Continue
    0.74
     glTexCoord
    0.72
     goto
    0.71
     UIApplication
    0.70
    ResumeLayout
    0.69
    Act Density 0.096%

    No Known Activations