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

    Neuronpedia

    INDEX
    Explanations

    Translate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resilience
    -0.07
     etme
    -0.07
    LD
    -0.07
    _ipc
    -0.07
    _priority
    -0.06
    _MET
    -0.06
    doctor
    -0.06
     estado
    -0.06
    rotation
    -0.06
    ıs
    -0.06
    POSITIVE LOGITS
    >`;↵
    0.07
    iếm
    0.06
    ».
    0.06
    [Double
    0.06
     Translate
    0.06
     kişiler
    0.06
    ें↵↵
    0.06
     ।↵
    0.06
    @click
    0.06
    ]
↵
    0.06
    Act Density 0.006%

    No Known Activations