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

    Neuronpedia

    INDEX
    Explanations

    Balance and support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    က
    -0.08
    increment
    -0.08
    aseq
    -0.08
    _days
    -0.07
    isdigit
    -0.07
    ाप
    -0.07
     grotes
    -0.07
     nightmare
    -0.07
    過
    -0.07
    ား
    -0.07
    POSITIVE LOGITS
     safety
    0.09
     стены
    0.09
     arrested
    0.08
     bunda
    0.08
     tangan
    0.08
     удалить
    0.08
    имо
    0.08
     rail
    0.08
     Veilig
    0.08
    idenav
    0.08
    Act Density 0.007%

    No Known Activations