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

    Neuronpedia

    INDEX
    Explanations

    hope

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	br
    -0.07
     cours
    -0.07
     bowling
    -0.07
    になり
    -0.07
    Going
    -0.07
     zombies
    -0.06
     rw
    -0.06
     Lebanese
    -0.06
     přitom
    -0.06
    音
    -0.06
    POSITIVE LOGITS
    lightly
    0.06
     ssid
    0.06
    >+
    0.06
    мос
    0.06
    _failure
    0.06
    wand
    0.06
    —or
    0.06
    �
    0.06
    antine
    0.06
     Knicks
    0.06
    Act Density 0.099%

    No Known Activations