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

    Neuronpedia

    INDEX
    Explanations

    leading projects and initiatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     underlying
    0.40
    ১
    0.39
     Underlying
    0.38
    ohid
    0.38
    веде
    0.38
     upon
    0.38
    מש
    0.37
    டுகின்றன
    0.37
     liberd
    0.36
    mam
    0.36
    POSITIVE LOGITS
     astray
    1.15
     charge
    0.71
     efforts
    0.67
    charge
    0.61
    ership
    0.58
     initiatives
    0.57
     iniciativas
    0.56
     negotiations
    0.56
    ERSHIP
    0.56
     discussions
    0.55
    Act Density 0.021%

    No Known Activations