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

    Neuronpedia

    INDEX
    Explanations

    HVAC systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    משל
    -0.07
    ="<
    -0.07
    .Platform
    -0.07
     quitting
    -0.06
     Attention
    -0.06
    솤
    -0.06
    /my
    -0.06
    see
    -0.06
     tale
    -0.06
    etc
    -0.06
    POSITIVE LOGITS
    сор
    0.07
    TING
    0.07
     hur
    0.07
     선택
    0.07
     filt
    0.07
    ❃
    0.06
    𝐤
    0.06
    튬
    0.06
     ativ
    0.06
     Hon
    0.06
    Act Density 0.039%

    No Known Activations