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

    Neuronpedia

    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	start
    -0.07
    efa
    -0.07
    /article
    -0.06
    dismiss
    -0.06
    _FIFO
    -0.06
    _RAM
    -0.06
     xyz
    -0.06
    RR
    -0.05
    _epi
    -0.05
    COMP
    -0.05
    POSITIVE LOGITS
     teammates
    0.07
     thankfully
    0.07
    arming
    0.07
    (propertyName
    0.07
     rug
    0.06
     unpopular
    0.06
    (sock
    0.06
     ):↵
    0.06
    (binary
    0.06
    beans
    0.06
    Act Density 0.007%

    No Known Activations