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

    Neuronpedia

    INDEX
    Explanations

    modal verbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quartered
    -0.07
     στην
    -0.06
     Es
    -0.06
     Hyderabad
    -0.06
    "></
    -0.06
     exploded
    -0.06
    ками
    -0.06
    anghai
    -0.06
     buckets
    -0.06
    ry
    -0.06
    POSITIVE LOGITS
    _reply
    0.07
     whose
    0.07
     keeper
    0.07
     will
    0.06
     slightest
    0.06
    /xhtml
    0.06
    will
    0.06
    _FILENAME
    0.06
    bellion
    0.06
    -conf
    0.06
    Act Density 0.103%

    No Known Activations