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

    Neuronpedia

    INDEX
    Explanations

    Psychology Today Therapist Finder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ों
    1.10
    ਾਂ
    0.99
    ان
    0.99
     citing
    0.89
     fledgling
    0.88
     father
    0.86
     predecessors
    0.85
    jpuri
    0.85
    पर
    0.84
    okines
    0.84
    POSITIVE LOGITS
    $.
    0.94
    t
    0.92
    ल्याण
    0.92
     groep
    0.86
    Truly
    0.86
    >*
    0.84
    suited
    0.84
    Expl
    0.84
    tiene
    0.84
    𝚝
    0.84
    Act Density 0.001%

    No Known Activations