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

    Neuronpedia

    INDEX
    Explanations

    ripe fruits and foods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    g
    1.00
    the
    0.98
    t
    0.96
    ing
    0.88
    two
    0.88
    w
    0.85
    ens
    0.84
    tr
    0.84
    quela
    0.83
    ные
    0.83
    POSITIVE LOGITS
    و
    0.91
    స్
    0.88
    ْم
    0.84
    ו
    0.81
     एकड़
    0.80
     Schon
    0.80
    ：
    0.79
     antics
    0.75
     CASCADE
    0.75
     vanlig
    0.75
    Act Density 0.002%

    No Known Activations