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

    Neuronpedia

    INDEX
    Explanations

    General requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Attractive
    0.43
    利
    0.43
     Utilization
    0.41
    Introduceti
    0.40
    stift
    0.40
    Variants
    0.40
    PRF
    0.40
    Utilization
    0.39
     상세
    0.39
     suất
    0.39
    POSITIVE LOGITS
    ouard
    0.40
    queda
    0.38
     tend
    0.38
     nec
    0.37
     guilty
    0.37
     dying
    0.37
    कमा
    0.37
    坍
    0.36
    aquin
    0.36
    收款
    0.35
    Act Density 0.000%

    No Known Activations