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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     comb
    -0.06
    .ReadUInt
    -0.06
     sensual
    -0.06
     sled
    -0.06
    амп
    -0.06
     textual
    -0.06
     blonde
    -0.06
    Thumb
    -0.06
    	BOOL
    -0.06
    	suite
    -0.06
    POSITIVE LOGITS
     #$
    0.07
    ací
    0.06
     underestimated
    0.06
     %"
    0.06
     adolescente
    0.06
    هـ
    0.06
     optimize
    0.06
    csrf
    0.06
    _remote
    0.06
    ับท
    0.06
    Act Density 0.012%

    No Known Activations