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

    Neuronpedia

    INDEX
    Explanations

    sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offsetX
    -0.07
    bia
    -0.06
     мужчин
    -0.06
     fayd
    -0.06
    _cuda
    -0.06
    782
    -0.06
    .visitVarInsn
    -0.06
    zp
    -0.06
     PIXI
    -0.06
    こと
    -0.06
    POSITIVE LOGITS
     Designed
    0.08
    Signing
    0.08
     wishes
    0.08
    issan
    0.07
    intptr
    0.07
     már
    0.07
     Sergeant
    0.07
    trasound
    0.07
    長
    0.07
    Taken
    0.06
    Act Density 0.005%

    No Known Activations