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

    Neuronpedia

    INDEX
    Explanations

    time units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Clothing
    -0.09
     ecu
    -0.08
     clues
    -0.08
     inequality
    -0.08
     juuri
    -0.07
    iful
    -0.07
     Defense
    -0.07
     desigual
    -0.07
    /ap
    -0.07
     hint
    -0.07
    POSITIVE LOGITS
    _done
    0.08
     זמן
    0.08
    .makedirs
    0.08
    pesas
    0.08
    работка
    0.08
    Assess
    0.08
     done
    0.08
    "]))↵
    0.08
     ganó
    0.08
     dauern
    0.08
    Act Density 0.011%

    No Known Activations