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

    Neuronpedia

    INDEX
    Explanations

    Fire TV execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ransport
    0.81
     ungg
    0.75
     ايا
    0.74
     maggior
    0.73
    addPreferred
    0.73
     беременности
    0.72
     logro
    0.72
    opters
    0.72
    коменду
    0.71
     ഉറ
    0.68
    POSITIVE LOGITS
    త్వం
    0.72
    త్స
    0.67
    uité
    0.67
     decompose
    0.63
     somewhere
    0.61
    Pv
    0.60
     sen
    0.59
    ständig
    0.59
    stmt
    0.59
     condition
    0.58
    Act Density 0.011%

    No Known Activations