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

    Neuronpedia

    INDEX
    Explanations

    izing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     week
    -0.07
    annies
    -0.07
     weekend
    -0.07
    �
    -0.07
     washing
    -0.07
    ē
    -0.07
     تصم
    -0.06
    inne
    -0.06
     married
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    ７
    0.07
    trees
    0.06
    Important
    0.06
     initiating
    0.06
    POSITE
    0.06
    684
    0.06
    alers
    0.06
     tagging
    0.06
    .ErrorMessage
    0.06
    _SPELL
    0.06
    Act Density 0.000%

    No Known Activations