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

    Neuronpedia

    INDEX
    Explanations

    phys

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ooth
    -0.07
     Og
    -0.06
     referencia
    -0.06
     bearings
    -0.06
     erotisk
    -0.06
    	swap
    -0.06
    _CHANNELS
    -0.06
    "At
    -0.06
     headed
    -0.06
     titled
    -0.06
    POSITIVE LOGITS
     Phil
    0.07
     Werner
    0.07
     stě
    0.07
    Props
    0.07
     startPos
    0.06
     hangi
    0.06
     نسمة
    0.06
     PHYS
    0.06
    ких
    0.06
     unc
    0.06
    Act Density 0.005%

    No Known Activations