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

    Neuronpedia

    INDEX
    Explanations

    job skills

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    compose
    -0.07
    basis
    -0.06
     Zoe
    -0.06
     Σα
    -0.06
    histoire
    -0.06
    -picker
    -0.06
    pher
    -0.06
     Joey
    -0.06
    contenido
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    ("""↵
    0.07
    ển
    0.07
     (("
    0.07
    ovém
    0.06
    acaktır
    0.06
     worksheet
    0.06
    >.↵↵
    0.06
    ’m
    0.06
     ```↵
    0.06
    )*(
    0.06
    Act Density 0.039%

    No Known Activations