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

    Neuronpedia

    INDEX
    Explanations

    . and -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cur
    -0.07
     sushi
    -0.06
     Leave
    -0.06
     fon
    -0.06
     управления
    -0.06
    	assertThat
    -0.06
     Ngoài
    -0.06
     Jog
    -0.06
    ीध
    -0.06
    жі
    -0.06
    POSITIVE LOGITS
    super
    0.06
    UTIL
    0.06
     preca
    0.06
    209
    0.06
    _WEAPON
    0.06
    panion
    0.06
     uncommon
    0.06
    .Signal
    0.06
    _attack
    0.06
     beforeEach
    0.06
    Act Density 0.057%

    No Known Activations