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
     αρ
    -0.07
    ulması
    -0.07
    WHO
    -0.06
    ाँ
    -0.06
     mastur
    -0.06
    計
    -0.06
    �
    -0.06
     кар
    -0.06
     strstr
    -0.06
     Tasmania
    -0.06
    POSITIVE LOGITS
    .middleware
    0.07
    Activation
    0.07
     цвет
    0.06
    _gradient
    0.06
     boasting
    0.06
     comply
    0.06
     specializing
    0.06
     govern
    0.06
    dart
    0.06
    .detach
    0.06
    Act Density 0.047%

    No Known Activations