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

    Neuronpedia

    INDEX
    Explanations

    else

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    _restart
    -0.06
    Jvm
    -0.06
    .cam
    -0.06
    Trip
    -0.06
    .vertx
    -0.06
     Symposium
    -0.06
    Pad
    -0.06
    .ff
    -0.06
    _ff
    -0.06
    POSITIVE LOGITS
     else
    0.08
    .but
    0.07
    .Here
    0.07
    	else
    0.07
     Gret
    0.07
    ")
↵
↵
    0.07
     underscores
    0.07
    (tweet
    0.07
    	widget
    0.06
     vídeo
    0.06
    Act Density 0.010%

    No Known Activations