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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vielen
    -0.07
     Alps
    -0.06
     Sand
    -0.06
     Subtract
    -0.06
     confession
    -0.06
     Tanzania
    -0.06
     MacBook
    -0.06
     Erotik
    -0.06
    ив
    -0.06
     epic
    -0.06
    POSITIVE LOGITS
    络
    0.06
    urança
    0.06
    ughter
    0.06
    .Entities
    0.06
    lerinin
    0.06
    ocop
    0.06
     hỏi
    0.06
    Searching
    0.06
    阅
    0.06
     newPassword
    0.06
    Act Density 0.001%

    No Known Activations