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

    Neuronpedia

    INDEX
    Explanations

    iron

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     служби
    -0.07
    Jud
    -0.07
    overview
    -0.06
     racing
    -0.06
    _bridge
    -0.06
     başında
    -0.06
    番号
    -0.06
     mềm
    -0.06
    _mass
    -0.06
     Drum
    -0.06
    POSITIVE LOGITS
    summer
    0.08
    Summer
    0.07
        	
↵
    0.07
    getChild
    0.06
     salvation
    0.06
     humanity
    0.06
    .imageView
    0.06
     Wrong
    0.06
     lunches
    0.06
     accession
    0.06
    Act Density 0.003%

    No Known Activations