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

    Neuronpedia

    INDEX
    Explanations

    float

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ber
    -0.07
    >e
    -0.06
    umably
    -0.06
    Debugger
    -0.06
     apologize
    -0.06
     Kendall
    -0.06
     scratched
    -0.06
    icol
    -0.06
     �
    -0.06
    dea
    -0.06
    POSITIVE LOGITS
     directs
    0.07
     První
    0.07
     team
    0.06
     queues
    0.06
    	Size
    0.06
     ENABLE
    0.06
     Assault
    0.06
     이용
    0.06
     방법
    0.06
    響
    0.06
    Act Density 0.006%

    No Known Activations