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

    Neuronpedia

    INDEX
    Explanations

    Lie

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     RAF
    -0.07
    @Web
    -0.07
    甲
    -0.06
    突发事件
    -0.06
     technician
    -0.06
     分
    -0.06
    .ge
    -0.06
    IFF
    -0.06
    Jackson
    -0.06
    POSITIVE LOGITS
    煃
    0.08
    进程
    0.08
     tongues
    0.07
    optimizer
    0.07
     surged
    0.07
     joystick
    0.07
    	lock
    0.07
    ют
    0.07
    iggers
    0.07
    _RING
    0.07
    Act Density 0.001%

    No Known Activations