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

    Neuronpedia

    INDEX
    Explanations

    Pop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CHEDULE
    -0.07
     prostor
    -0.06
     xmin
    -0.06
     cn
    -0.06
     Bes
    -0.06
     Rows
    -0.06
     воды
    -0.06
     cafeteria
    -0.06
    ника
    -0.06
    ists
    -0.06
    POSITIVE LOGITS
    ={{↵
    0.07
    _SORT
    0.07
    quired
    0.07
     Infect
    0.06
     asks
    0.06
     ask
    0.06
    _EQUAL
    0.06
     casos
    0.06
    erguson
    0.06
     masturbation
    0.06
    Act Density 0.001%

    No Known Activations