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

    Neuronpedia

    INDEX
    Explanations

    libertarianism

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    撖
    -0.07
    	Update
    -0.07
    뻅
    -0.07
     Neck
    -0.07
    byss
    -0.07
    icipation
    -0.07
     En
    -0.06
    뗏
    -0.06
    reserved
    -0.06
    	files
    -0.06
    POSITIVE LOGITS
    mutation
    0.08
    osta
    0.08
    𒋗
    0.07
    mount
    0.07
     Sustainable
    0.07
     источник
    0.07
     gouver
    0.07
     schematic
    0.07
     changer
    0.07
    נקודת
    0.07
    Act Density 0.027%

    No Known Activations