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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ACL
    -0.07
    Li
    -0.07
    Metal
    -0.06
     Scripts
    -0.06
    perienced
    -0.06
    FilterWhere
    -0.06
    .What
    -0.06
     manifests
    -0.06
     lm
    -0.06
    ocrat
    -0.06
    POSITIVE LOGITS
     childhood
    0.07
    Fresh
    0.07
    Ế
    0.06
     další
    0.06
     başlam
    0.06
    vě
    0.06
     fruitful
    0.06
    化
    0.06
     बनन
    0.06
    spot
    0.06
    Act Density 0.015%

    No Known Activations