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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Farms
    0.38
     of
    0.37
     Operating
    0.37
     Sharp
    0.37
     affez
    0.37
    ment
    0.36
    Від
    0.36
    Α
    0.35
    aky
    0.34
     internos
    0.34
    POSITIVE LOGITS
     exfol
    0.40
     unmistak
    0.40
     obfusc
    0.38
     nginx
    0.38
    ッチン
    0.37
     쿠
    0.37
     neutrophil
    0.37
     niacin
    0.36
     neurotrans
    0.35
     cheating
    0.35
    Act Density 0.001%

    No Known Activations