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

    Neuronpedia

    INDEX
    Explanations

    appreciation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Null
    -0.07
     Sand
    -0.07
     Constraints
    -0.06
    _wind
    -0.06
    ACITY
    -0.06
     Wand
    -0.06
    asad
    -0.06
    (stdout
    -0.06
     Ernst
    -0.06
     Naughty
    -0.06
    POSITIVE LOGITS
     appreciate
    0.12
     appreciated
    0.11
     appreciation
    0.11
     apprec
    0.08
    repair
    0.08
     agre
    0.07
     respecting
    0.07
            
↵        
↵
    0.07
     Apprec
    0.07
    。↵
    0.07
    Act Density 0.012%

    No Known Activations