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

    Neuronpedia

    INDEX
    Explanations

    s'mores, camping and alfresco dining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ok
    1.01
    ä
    0.84
    ?
    0.75
    :
    0.74
    A
    0.73
     IAAF
    0.69
    rakech
    0.68
    hui
    0.67
    rel
    0.66
     DJs
    0.66
    POSITIVE LOGITS
     be
    0.79
     cuộc
    0.76
    ير
    0.74
    و
    0.74
    ן
    0.74
     can
    0.72
    نا
    0.72
    یر
    0.72
     domínio
    0.71
    ॉर्ट
    0.69
    Act Density 0.001%

    No Known Activations