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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المق
    -0.07
     뭐
    -0.07
     можна
    -0.07
    bearer
    -0.07
     kvůli
    -0.07
    '-
    -0.07
    (()
    -0.07
    适
    -0.07
    "While
    -0.06
    squeeze
    -0.06
    POSITIVE LOGITS
     EXEMPLARY
    0.06
     information
    0.06
    Joseph
    0.06
     ciudad
    0.06
    icut
    0.06
    lah
    0.06
     esteemed
    0.06
    knowledge
    0.06
     autistic
    0.05
    usher
    0.05
    Act Density 0.000%

    No Known Activations