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

    Neuronpedia

    INDEX
    Explanations

    Code/data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BaseType
    -0.07
    _blocking
    -0.07
     Luke
    -0.07
    (Tag
    -0.07
     Европ
    -0.07
    /sm
    -0.06
    Tipo
    -0.06
    _pag
    -0.06
    braco
    -0.06
     servic
    -0.06
    POSITIVE LOGITS
     воды
    0.06
    níků
    0.06
    harma
    0.06
     {}",
    0.06
     warn
    0.06
     $"{
    0.05
    emplate
    0.05
    stal
    0.05
    orna
    0.05
     �
    0.05
    Act Density 0.195%

    No Known Activations