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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     breathtaking
    -0.07
     boyc
    -0.07
     PARK
    -0.07
     Park
    -0.07
    '
    -0.06
    cw
    -0.06
    mass
    -0.06
     mass
    -0.06
     Gordon
    -0.06
    	object
    -0.06
    POSITIVE LOGITS
     contributes
    0.06
     complain
    0.06
     excessively
    0.06
     heraus
    0.06
     Function
    0.06
    อล
    0.06
    умент
    0.06
     nominate
    0.06
     Vietnamese
    0.06
     elevator
    0.06
    Act Density 0.003%

    No Known Activations