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

    Neuronpedia

    INDEX
    Explanations

    strange looks from strangers

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    са
    -0.06
    -centric
    -0.06
    太太
    -0.06
    Mutex
    -0.06
     ruthless
    -0.06
    *cos
    -0.06
    椁
    -0.06
    桡
    -0.06
    鼍
    -0.06
    *angstrom
    -0.06
    POSITIVE LOGITS
    0.08
     Produce
    0.07
    Jac
    0.07
     càng
    0.07
    iei
    0.07
     projectiles
    0.07
     Rihanna
    0.07
    Pick
    0.07
    CORE
    0.07
     #####
    0.06
    Act Density 0.057%

    No Known Activations