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

    Neuronpedia

    INDEX
    Explanations

    PDDL domain and parameter definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PDEs
    0.40
     mei
    0.39
    returned
    0.38
    INTa
    0.37
     вернуть
    0.37
     SOL
    0.37
    стина
    0.36
     kh
    0.36
     returned
    0.36
    奶奶
    0.36
    POSITIVE LOGITS
    rtype
    0.57
    param
    0.45
     param
    0.41
    rparam
    0.40
    .`);
    0.39
    etype
    0.39
    type
    0.39
    ertype
    0.38
    help
    0.37
    ində
    0.36
    Act Density 0.002%

    No Known Activations