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

    Neuronpedia

    INDEX
    Explanations

    size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    נזק
    -0.07
     MessageBoxIcon
    -0.07
     dns
    -0.07
    marketing
    -0.06
    ENV
    -0.06
    Authenticate
    -0.06
    Ang
    -0.06
     suspect
    -0.06
    غضب
    -0.06
     Zhao
    -0.06
    POSITIVE LOGITS
    .cms
    0.07
    .enabled
    0.07
    _EPS
    0.07
    	ent
    0.07
     камер
    0.07
    ей
    0.07
    .iterator
    0.06
    ALS
    0.06
    eful
    0.06
    idas
    0.06
    Act Density 0.118%

    No Known Activations