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

    Neuronpedia

    INDEX
    Explanations

    creating new instances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noble
    0.41
    :[/
    0.38
    煖
    0.38
    ];//
    0.37
     കു
    0.36
     schol
    0.36
     देखा
    0.36
    .;
    0.35
     온
    0.35
     Nearest
    0.35
    POSITIVE LOGITS
    true
    0.52
     val
    0.49
    val
    0.45
    returns
    0.43
     true
    0.42
    ook
    0.40
    new
    0.40
    にする
    0.40
     returns
    0.39
    assurance
    0.39
    Act Density 0.019%

    No Known Activations