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

    Neuronpedia

    INDEX
    Explanations

    asterisk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .T
    -0.07
    .column
    -0.07
    '>↵
    -0.07
    .people
    -0.07
     ],
    -0.07
    ωση
    -0.06
    ِن
    -0.06
    _company
    -0.06
    _header
    -0.06
    exec
    -0.06
    POSITIVE LOGITS
     Charlie
    0.06
     réfé
    0.06
    .sock
    0.06
     subst
    0.06
    léd
    0.06
    짝
    0.06
     yard
    0.06
    ІІ
    0.06
    -cat
    0.06
    かの
    0.06
    Act Density 0.001%

    No Known Activations