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

    Neuronpedia

    INDEX
    Explanations

    hard followed by work or rock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ย
    0.81
    이터
    0.79
    青少年
    0.79
    ATORS
    0.79
    Enhanced
    0.79
     обслу
    0.79
    Bulletin
    0.78
    Mutability
    0.77
    滃
    0.77
    מית
    0.75
    POSITIVE LOGITS
    wired
    1.66
    boiled
    1.41
    coded
    1.40
    wiring
    1.31
    nosed
    1.26
    core
    1.23
     fought
    1.19
    ening
    1.17
    wearing
    1.16
    ened
    1.15
    Act Density 0.042%

    No Known Activations