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

    Neuronpedia

    INDEX
    Explanations

    comment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    िकट
    -0.07
    (S
    -0.06
    _REGISTRY
    -0.06
    هد
    -0.06
    914
    -0.06
    죠
    -0.06
    !!!
    -0.06
    ——
    -0.06
    #"
    -0.06
    /sec
    -0.06
    POSITIVE LOGITS
     borderRadius
    0.07
     IH
    0.06
     лож
    0.06
     Dave
    0.06
     waking
    0.06
    urally
    0.06
     Ron
    0.06
     inher
    0.06
    ひと
    0.06
     Constraints
    0.06
    Act Density 0.002%

    No Known Activations