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

    Neuronpedia

    INDEX
    Explanations

    repeat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bowen
    -0.07
    .ball
    -0.07
     cerv
    -0.07
    vature
    -0.07
     sorting
    -0.07
    observation
    -0.06
     Mercer
    -0.06
    _Property
    -0.06
     tumble
    -0.06
     breaker
    -0.06
    POSITIVE LOGITS
     Once
    0.07
    ')↵↵↵↵
    0.06
    =='
    0.06
     तत
    0.06
    Once
    0.06
     अगल
    0.06
    HostName
    0.06
    orarily
    0.06
     téměř
    0.06
    Rather
    0.06
    Act Density 0.004%

    No Known Activations