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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SHA
    -0.06
    infile
    -0.06
     hastalık
    -0.06
     reloading
    -0.06
    __',
    -0.06
    恋
    -0.06
     Spo
    -0.06
    الث
    -0.06
    rupt
    -0.06
     whispers
    -0.06
    POSITIVE LOGITS
    γει
    0.07
     environments
    0.06
     vyb
    0.06
    .Ver
    0.06
    紹
    0.06
    zego
    0.06
     националь
    0.06
     contexts
    0.06
    ภาษ
    0.06
    minor
    0.06
    Act Density 0.000%

    No Known Activations