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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     emphasized
    -0.07
     visualization
    -0.07
     mor
    -0.07
    资源
    -0.07
     error
    -0.07
     sia
    -0.06
     vulnerability
    -0.06
    India
    -0.06
     panda
    -0.06
    ži
    -0.06
    POSITIVE LOGITS
    ２０
    0.07
     graphite
    0.07
    十一
    0.07
    RIPTION
    0.07
    Про
    0.07
     �
    0.07
    attro
    0.07
     вз
    0.07
     #{@
    0.06
     Ap
    0.06
    Act Density 0.019%

    No Known Activations