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

    Neuronpedia

    INDEX
    Explanations

    mean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Legal
    -0.06
    '){
↵
    -0.06
    Hopefully
    -0.06
    Entry
    -0.06
    .).↵↵
    -0.06
    Vent
    -0.06
     ');
↵
    -0.06
     охорони
    -0.06
    .defaults
    -0.06
     -->
↵
    -0.06
    POSITIVE LOGITS
    ropsych
    0.07
     Gew
    0.06
     juegos
    0.06
    ASURE
    0.06
     professionalism
    0.06
    _contacts
    0.06
     багат
    0.06
     provoked
    0.06
    esses
    0.06
     rumor
    0.06
    Act Density 0.063%

    No Known Activations