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

    Neuronpedia

    INDEX
    Explanations

    touching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yl
    -0.07
    Ω
    -0.06
    adores
    -0.06
     languages
    -0.06
     compound
    -0.06
     cancers
    -0.06
     mic
    -0.06
     servers
    -0.06
    .ps
    -0.06
     flavours
    -0.06
    POSITIVE LOGITS
    idelity
    0.08
     Casa
    0.06
    ImplOptions
    0.06
     confined
    0.06
     kendisine
    0.06
     independ
    0.06
    시는
    0.06
    HttpContext
    0.06
    	Main
    0.06
     incontr
    0.06
    Act Density 0.035%

    No Known Activations