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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     handshake
    -0.08
     kì
    -0.07
    .application
    -0.07
     run
    -0.07
    (en
    -0.06
    	initial
    -0.06
    ACTION
    -0.06
     Elder
    -0.06
     illust
    -0.06
    召
    -0.06
    POSITIVE LOGITS
    _LOG
    0.07
     PWM
    0.07
     cultivating
    0.07
     Mathf
    0.07
     Республи
    0.07
    _traffic
    0.06
    orb
    0.06
    .Prot
    0.06
     phy
    0.06
    /Observable
    0.06
    Act Density 0.003%

    No Known Activations