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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Saharan
    -0.07
     IPv
    -0.07
    positive
    -0.07
    Imagine
    -0.07
    Retention
    -0.07
    -send
    -0.06
     eher
    -0.06
    _Parse
    -0.06
    تبار
    -0.06
    (dic
    -0.06
    POSITIVE LOGITS
     čtyři
    0.06
    'A
    0.06
     вок
    0.06
     dob
    0.06
     impressed
    0.06
    096
    0.06
    ա
    0.06
    AZY
    0.06
    Tokens
    0.06
    285
    0.06
    Act Density 0.497%

    No Known Activations