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

    Neuronpedia

    INDEX
    Explanations

    model response indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forensics
    0.44
    ައ
    0.44
     cmdlet
    0.43
     যখন
    0.43
    mdui
    0.41
     epub
    0.40
     similarity
    0.40
     stderr
    0.40
     errors
    0.39
    ハート
    0.39
    POSITIVE LOGITS
    Okay
    0.63
    Alright
    0.62
    Here
    0.62
    Vacc
    0.56
    Now
    0.55
    Before
    0.55
    Immediately
    0.53
    Respiratory
    0.51
    Notable
    0.51
     Here
    0.51
    Act Density 1.846%

    No Known Activations