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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     options
    -0.07
    rients
    -0.07
     foam
    -0.07
     �
    -0.06
    .toastr
    -0.06
     활동
    -0.06
    只
    -0.06
     studying
    -0.06
    ोप
    -0.06
     gia
    -0.06
    POSITIVE LOGITS
     halten
    0.07
     =================================================================================
    0.07
    	iter
    0.06
     прес
    0.06
    giatan
    0.06
     Akron
    0.06
     gefunden
    0.06
    ící
    0.06
     것으로
    0.06
     converged
    0.06
    Act Density 0.043%

    No Known Activations