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

    Neuronpedia

    INDEX
    Explanations

    filtered

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     нали
    -0.07
     meld
    -0.07
    ็นท
    -0.06
    vik
    -0.06
     Cunning
    -0.06
     आप
    -0.06
    ُّ
    -0.06
    命令
    -0.06
    jh
    -0.06
    lya
    -0.06
    POSITIVE LOGITS
     Admin
    0.07
     abs
    0.06
     monet
    0.06
    filtered
    0.06
                         ↵
    0.06
            
↵
    0.06
     Honestly
    0.06
    .sup
    0.06
     restraint
    0.06
    .Rotate
    0.06
    Act Density 0.004%

    No Known Activations