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

    Neuronpedia

    INDEX
    Explanations

    negativity and pessimism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     стала
    -0.07
     Enabled
    -0.07
    Za
    -0.07
    Customer
    -0.07
    !!↵↵
    -0.06
    Enabled
    -0.06
    γο
    -0.06
    γ
    -0.06
    ्थन
    -0.06
    Mob
    -0.06
    POSITIVE LOGITS
     manufactured
    0.08
    _SCRIPT
    0.07
     fif
    0.07
    mort
    0.06
     overloaded
    0.06
     รอบ
    0.06
     uploading
    0.06
    �
    0.06
     kardeş
    0.06
    .Sqrt
    0.06
    Act Density 0.098%

    No Known Activations