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

    Neuronpedia

    INDEX
    Explanations

    contingency, potential issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ih
    -0.07
    iti
    -0.07
    alli
    -0.07
    <|im_end|>
    -0.07
     lecturer
    -0.07
    _MIN
    -0.07
    Longitude
    -0.07
     CCT
    -0.06
    中国电信
    -0.06
     appointment
    -0.06
    POSITIVE LOGITS
    �
    0.07
     혹
    0.07
    越发
    0.07
    ower
    0.07
    story
    0.07
    덞
    0.07
    _ERRORS
    0.07
     backstory
    0.07
    收缩
    0.07
     בעוד
    0.06
    Act Density 0.080%

    No Known Activations