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

    Neuronpedia

    INDEX
    Explanations

    heat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Surely
    -0.07
     phenomenal
    -0.06
    serir
    -0.06
     blood
    -0.06
     intent
    -0.06
     approach
    -0.06
    Toronto
    -0.06
    threshold
    -0.06
     Trent
    -0.06
    original
    -0.06
    POSITIVE LOGITS
    '])){↵
    0.07
    ์)
    0.07
    >\<^
    0.07
    ).'</
    0.06
    
    0.06
    (".")
    0.06
    ...)
    0.06
    �
    0.06
    (Gtk
    0.06
     в
    0.06
    Act Density 0.008%

    No Known Activations