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

    Neuronpedia

    INDEX
    Explanations

    ).

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spp
    -0.07
    Handles
    -0.07
     벽
    -0.07
     Thumb
    -0.07
    -corner
    -0.06
    Surv
    -0.06
     Spacer
    -0.06
    igeria
    -0.06
     spéc
    -0.06
    Hand
    -0.06
    POSITIVE LOGITS
    *↵↵
    0.07
     αυ
    0.06
     stay
    0.06
    _pick
    0.06
     г
    0.06
     lifespan
    0.06
     purity
    0.06
    	AL
    0.06
     Nicholas
    0.06
    حد
    0.06
    Act Density 0.062%

    No Known Activations