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

    Neuronpedia

    INDEX
    Explanations

    -tion concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    性の
    0.39
    sed
    0.37
    聖
    0.36
    ชนิด
    0.36
    baked
    0.32
    性
    0.32
     concord
    0.31
    hall
    0.31
    soaked
    0.31
    seg
    0.30
    POSITIVE LOGITS
     Violation
    0.48
     Motivation
    0.48
     Deviation
    0.47
     Transitions
    0.46
     Financial
    0.46
     Challenges
    0.45
     Formation
    0.45
     Thermal
    0.45
     Food
    0.45
     Transition
    0.44
    Act Density 0.000%

    No Known Activations