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

    Neuronpedia

    INDEX
    Explanations

    playground safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GSM
    -0.09
     hambre
    -0.08
     batterij
    -0.08
     Gibbs
    -0.08
     �
    -0.08
     wavelength
    -0.08
    .commun
    -0.07
     Werden
    -0.07
    Budget
    -0.07
     agencias
    -0.07
    POSITIVE LOGITS
     safety
    0.16
     Safety
    0.15
    Safety
    0.15
     안전
    0.14
     safer
    0.14
     safest
    0.14
    安全
    0.14
     सुरक्षित
    0.13
     സുരക്ഷ
    0.13
     güven
    0.12
    Act Density 0.058%

    No Known Activations