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

    Neuronpedia

    INDEX
    Explanations

    the and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inclu
    -0.07
    Pressure
    -0.07
     slaves
    -0.06
     pregnancy
    -0.06
     Specific
    -0.06
     attitudes
    -0.06
     Pressure
    -0.06
     drawings
    -0.06
    Consult
    -0.06
     hik
    -0.06
    POSITIVE LOGITS
     anonym
    0.07
    Meteor
    0.06
    ательно
    0.06
     необхідно
    0.06
    _crop
    0.06
     muddy
    0.06
    해야
    0.06
     denies
    0.06
    translated
    0.06
    +");↵
    0.06
    Act Density 0.021%

    No Known Activations