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

    Neuronpedia

    INDEX
    Explanations

    moment.js in javascript

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     positive
    0.38
     delta
    0.38
    XY
    0.38
    ائیں
    0.37
    ARGET
    0.37
    Merge
    0.37
    Dale
    0.36
    Num
    0.36
    INCRE
    0.36
    ATYPE
    0.36
    POSITIVE LOGITS
    unix
    0.46
    utc
    0.42
     validInput
    0.42
     parent
    0.39
    సరం
    0.38
    くれました
    0.38
    顿时
    0.38
    離婚
    0.38
    parent
    0.37
     தெரிவித்தார்
    0.37
    Act Density 0.001%

    No Known Activations