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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     off
    -0.84
    Off
    -0.79
     Off
    -0.79
    off
    -0.71
     OFF
    -0.69
    OFF
    -0.65
    fjspx
    -0.57
     beginnetje
    -0.57
    chede
    -0.56
    HostException
    -0.56
    POSITIVE LOGITS
    المكان
    0.55
    Šaltiniai
    0.54
     distanciation
    0.52
    teto
    0.52
     hers
    0.49
    ValueOf
    0.48
    ̈́
    0.48
    cloudflare
    0.47
     Ours
    0.47
     geldig
    0.47
    Act Density 0.024%

    No Known Activations