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

    Neuronpedia

    INDEX
    Explanations

    directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    िसक
    -0.07
     prat
    -0.06
     используют
    -0.06
     metam
    -0.06
    #,
    -0.06
     Alexa
    -0.06
    ，因
    -0.06
     ukáz
    -0.06
    _pres
    -0.06
    beans
    -0.06
    POSITIVE LOGITS
     Passive
    0.07
     Dortmund
    0.07
     deserted
    0.06
     louder
    0.06
     renters
    0.06
    Deleting
    0.06
    lef
    0.06
    :Event
    0.06
     Wrestling
    0.06
    inking
    0.06
    Act Density 0.010%

    No Known Activations