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

    Neuronpedia

    INDEX
    Explanations

    ability, capacity, tendency, intention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    There
    0.36
    )).
    0.35
     prevails
    0.35
    εις
    0.33
     Existe
    0.33
    liert
    0.33
     apparaissent
    0.33
    )],
    0.32
     fehlt
    0.32
     funcionalidades
    0.32
    POSITIVE LOGITS
     ability
    1.23
     willingness
    1.05
     inability
    1.02
     reliance
    0.94
     способность
    0.93
     dependence
    0.88
     insistence
    0.88
     adherence
    0.86
     Ability
    0.81
     unwillingness
    0.80
    Act Density 0.009%

    No Known Activations