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

    Neuronpedia

    INDEX
    Explanations

    viewed from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     follicles
    0.51
    グレ
    0.51
     Theorie
    0.48
    大
    0.47
    డ
    0.47
    Esper
    0.46
    OLE
    0.45
     olds
    0.44
     mech
    0.44
     NODE
    0.43
    POSITIVE LOGITS
    ophyll
    0.44
     customised
    0.40
     clear
    0.40
    sky
    0.39
    jeet
    0.39
    navigationLinks
    0.39
    aviti
    0.39
     vrlo
    0.39
    getTransforms
    0.39
     최대한
    0.39
    Act Density 0.043%

    No Known Activations