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

    Neuronpedia

    INDEX
    Explanations

    involve adding keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    coal
    0.38
     माइट
    0.38
    Coal
    0.37
     coal
    0.37
     préal
    0.36
     согласи
    0.36
     말미
    0.36
    ameleon
    0.35
     Jerusal
    0.35
    と同
    0.34
    POSITIVE LOGITS
    형
    0.45
     Giáo
    0.40
    ધાર
    0.38
    getTeam
    0.37
    漿
    0.37
    istic
    0.36
     athletics
    0.36
     Irma
    0.36
     Team
    0.35
     টিম
    0.35
    Act Density 0.000%

    No Known Activations