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

    Neuronpedia

    INDEX
    Explanations

    say ". word"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     smack
    -0.07
    颁
    -0.07
    ሊ
    -0.07
    苞
    -0.07
    旌
    -0.07
    拜师
    -0.07
    😬
    -0.07
    �
    -0.07
    Bru
    -0.07
    עס
    -0.07
    POSITIVE LOGITS
     operations
    0.08
     step
    0.08
    rete
    0.07
    roperties
    0.07
     history
    0.07
     studies
    0.07
     conducted
    0.07
    führt
    0.07
    ático
    0.07
    .execute
    0.07
    Act Density 0.000%

    No Known Activations