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

    Neuronpedia

    INDEX
    Explanations

    sequence number, flight delays, minimum price

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chloric
    0.43
    mad
    0.41
     cloning
    0.40
    नीत
    0.38
     mach
    0.38
     பாதை
    0.37
     ஆனது
    0.37
     vacc
    0.37
     mad
    0.37
     plating
    0.37
    POSITIVE LOGITS
     #
    0.75
    #
    0.68
     "#
    0.62
     hashtag
    0.59
     hashtags
    0.56
     #(
    0.55
     \#
    0.54
     (#
    0.53
    ]#
    0.51
    hasht
    0.50
    Act Density 0.000%

    No Known Activations