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

    Neuronpedia

    INDEX
    Explanations

    Relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (n
    -0.07
    python
    -0.06
    _hard
    -0.06
    _format
    -0.06
    ろう
    -0.06
     одним
    -0.06
    ると
    -0.06
     있던
    -0.06
    van
    -0.06
    bx
    -0.06
    POSITIVE LOGITS
     Sammy
    0.06
    -expression
    0.06
    CheckedChangeListener
    0.06
     agreed
    0.06
     querying
    0.06
    _ttl
    0.06
    ὶ
    0.06
     murky
    0.06
     organisms
    0.06
     صن
    0.06
    Act Density 0.020%

    No Known Activations