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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ansk
    -0.07
     Late
    -0.07
    -talk
    -0.07
     inherits
    -0.07
     tame
    -0.07
    .Save
    -0.06
    _cust
    -0.06
     explosive
    -0.06
     inequalities
    -0.06
     inert
    -0.06
    POSITIVE LOGITS
    ???
    0.07
    ,’”
    0.07
    preneur
    0.07
     often
    0.07
     Often
    0.07
     homeowners
    0.06
    external
    0.06
     conform
    0.06
    ??
    0.06
    имер
    0.06
    Act Density 0.018%

    No Known Activations