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

    Neuronpedia

    INDEX
    Explanations

    life choices and hacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iv
    0.43
    roits
    0.38
    dry
    0.36
    t
    0.36
    apply
    0.35
    org
    0.35
    ariance
    0.34
    ς
    0.34
    function
    0.34
    Custom
    0.34
    POSITIVE LOGITS
     expectancy
    0.81
    शैली
    0.63
     cotidiana
    0.62
    स्टाइल
    0.57
    boats
    0.51
     affirming
    0.51
     जीने
    0.49
     lived
    0.49
     삶
    0.48
    삶
    0.48
    Act Density 0.026%

    No Known Activations