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

    Neuronpedia

    INDEX
    Explanations

    muscle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     catastrophic
    -0.08
     veto
    -0.07
    .EventHandler
    -0.07
    igrated
    -0.07
     หาก
    -0.06
     方法
    -0.06
    olen
    -0.06
    itating
    -0.06
    ier
    -0.06
     collision
    -0.06
    POSITIVE LOGITS
     muscle
    0.10
     Muscle
    0.08
     INTERRUPTION
    0.07
    uld
    0.07
     SCALE
    0.07
    	model
    0.06
    'We
    0.06
     MSNBC
    0.06
     curry
    0.06
     Lace
    0.06
    Act Density 0.006%

    No Known Activations