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

    Neuronpedia

    INDEX
    Explanations

    safety assessments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ılmaz
    -0.07
    lamaktadır
    -0.07
    ٌ
    -0.07
    vio
    -0.07
     E
    -0.06
     YYYY
    -0.06
    .voice
    -0.06
    Recursive
    -0.06
    글상위
    -0.06
     Harrison
    -0.06
    POSITIVE LOGITS
    ettel
    0.08
    .TODO
    0.06
     قال
    0.06
    419
    0.06
     będą
    0.06
    ると
    0.06
     başvuru
    0.06
     Diese
    0.05
     أص
    0.05
     vois
    0.05
    Act Density 0.019%

    No Known Activations