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

    Neuronpedia

    INDEX
    Explanations

    heart

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icho
    -0.07
     impedance
    -0.06
    imid
    -0.06
    방
    -0.06
    æ
    -0.06
     bleed
    -0.06
    雅
    -0.06
     shadow
    -0.06
     sensor
    -0.06
     hale
    -0.06
    POSITIVE LOGITS
     scorer
    0.07
    ICY
    0.07
     misrepresented
    0.07
    /Form
    0.07
    .ObjectMeta
    0.07
     mrb
    0.06
    ]))
↵
    0.06
    Depart
    0.06
    ोस
    0.06
    .ends
    0.06
    Act Density 0.004%

    No Known Activations