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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assertion
    -0.07
    .No
    -0.07
    .cons
    -0.06
    /auth
    -0.06
    unker
    -0.06
    _altern
    -0.06
    RITE
    -0.06
    .us
    -0.06
    _CONF
    -0.06
     attract
    -0.06
    POSITIVE LOGITS
     obce
    0.07
     '').
    0.06
     grad
    0.06
    KANJI
    0.06
     kata
    0.06
    ebp
    0.06
     hPa
    0.06
    'nda
    0.06
     BIND
    0.06
     İş
    0.06
    Act Density 0.220%

    No Known Activations