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

    Neuronpedia

    INDEX
    Explanations

    affection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     biblical
    -0.07
    最初
    -0.07
     Reality
    -0.06
     viability
    -0.06
     Chaos
    -0.06
    .Transfer
    -0.06
     visions
    -0.06
    -metal
    -0.06
     Pivot
    -0.06
    .visualization
    -0.06
    POSITIVE LOGITS
     affection
    0.15
    .setEditable
    0.07
    .allow
    0.07
     rust
    0.07
    \:
    0.07
     uphol
    0.07
    ections
    0.07
            
↵        
↵
    0.07
     soph
    0.07
     PHI
    0.06
    Act Density 0.003%

    No Known Activations