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

    Neuronpedia

    INDEX
    Explanations

    overly tight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Goldberg
    0.52
     Nails
    0.46
     Zum
    0.45
    Zum
    0.42
     Height
    0.40
     Nearly
    0.40
     Breath
    0.40
     Clin
    0.40
     Rachel
    0.39
    UIControlState
    0.39
    POSITIVE LOGITS
     sosten
    0.45
     embrace
    0.44
     институ
    0.44
     sociedades
    0.42
     nationalists
    0.40
     norms
    0.40
     società
    0.40
     evo
    0.40
     есте
    0.40
     hygien
    0.39
    Act Density 0.001%

    No Known Activations